使用python pyhdfs操作hadoop 出现ConnectionError: HTTPConnectionPool(host='bigdata-senior03.chybinmy.com'

 

gaierror                                  Traceback (most recent call last)
C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\urllib3\connection.py in _new_conn(self)
    158             conn = connection.create_connection(
--> 159                 (self._dns_host, self.port), self.timeout, **extra_kw)
    160 

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\urllib3\util\connection.py in create_connection(address, timeout, source_address, socket_options)
     56 
---> 57     for res in socket.getaddrinfo(host, port, family, socket.SOCK_STREAM):
     58         af, socktype, proto, canonname, sa = res

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\socket.py in getaddrinfo(host, port, family, type, proto, flags)
    732     addrlist = []
--> 733     for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
    734         af, socktype, proto, canonname, sa = res

gaierror: [Errno 11001] getaddrinfo failed

During handling of the above exception, another exception occurred:

NewConnectionError                        Traceback (most recent call last)
C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\urllib3\connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)
    599                                                   body=body, headers=headers,
--> 600                                                   chunked=chunked)
    601 

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\urllib3\connectionpool.py in _make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
    353         else:
--> 354             conn.request(method, url, **httplib_request_kw)
    355 

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\http\client.py in request(self, method, url, body, headers)
   1106         """Send a complete request to the server."""
-> 1107         self._send_request(method, url, body, headers)
   1108 

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\http\client.py in _send_request(self, method, url, body, headers)
   1151             body = _encode(body, 'body')
-> 1152         self.endheaders(body)
   1153 

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\http\client.py in endheaders(self, message_body)
   1102             raise CannotSendHeader()
-> 1103         self._send_output(message_body)
   1104 

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\http\client.py in _send_output(self, message_body)
    933 
--> 934         self.send(msg)
    935         if message_body is not None:

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\http\client.py in send(self, data)
    876             if self.auto_open:
--> 877                 self.connect()
    878             else:

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\urllib3\connection.py in connect(self)
    180     def connect(self):
--> 181         conn = self._new_conn()
    182         self._prepare_conn(conn)

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\urllib3\connection.py in _new_conn(self)
    167             raise NewConnectionError(
--> 168                 self, "Failed to establish a new connection: %s" % e)
    169 

NewConnectionError: : Failed to establish a new connection: [Errno 11001] getaddrinfo failed

During handling of the above exception, another exception occurred:

MaxRetryError                             Traceback (most recent call last)
C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\requests\adapters.py in send(self, request, stream, timeout, verify, cert, proxies)
    448                     retries=self.max_retries,
--> 449                     timeout=timeout
    450                 )

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\urllib3\connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)
    637             retries = retries.increment(method, url, error=e, _pool=self,
--> 638                                         _stacktrace=sys.exc_info()[2])
    639             retries.sleep()

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\urllib3\util\retry.py in increment(self, method, url, response, error, _pool, _stacktrace)
    397         if new_retry.is_exhausted():
--> 398             raise MaxRetryError(_pool, url, error or ResponseError(cause))
    399 

MaxRetryError: HTTPConnectionPool(host='bigdata-senior03.chybinmy.com', port=50075): Max retries exceeded with url: /webhdfs/v1/data/ah.txt?op=CREATE&user.name=root&namenoderpcaddress=bigdata-senior01.chybinmy.com:8020&createflag=&createparent=true&overwrite=false (Caused by NewConnectionError(': Failed to establish a new connection: [Errno 11001] getaddrinfo failed',))

During handling of the above exception, another exception occurred:

ConnectionError                           Traceback (most recent call last)
in ()
----> 1 client.copy_from_local("G:/安装文件/Readme.txt","/data/ah.txt")

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\pyhdfs.py in copy_from_local(self, localsrc, dest, **kwargs)
    751         """
    752         with io.open(localsrc, 'rb') as f:
--> 753             self.create(dest, f, **kwargs)
    754 
    755     def copy_to_local(self, src, localdest, **kwargs):

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\pyhdfs.py in create(self, path, data, **kwargs)
    424         assert not metadata_response.content
    425         data_response = self._requests_session.put(
--> 426             metadata_response.headers['location'], data=data, **self._requests_kwargs)
    427         _check_response(data_response, expected_status=httplib.CREATED)
    428         assert not data_response.content

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\requests\api.py in put(url, data, **kwargs)
    129     """
    130 
--> 131     return request('put', url, data=data, **kwargs)
    132 
    133 

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\requests\api.py in request(method, url, **kwargs)
     58     # cases, and look like a memory leak in others.
     59     with sessions.Session() as session:
---> 60         return session.request(method=method, url=url, **kwargs)
     61 
     62 

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\requests\sessions.py in request(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)
    531         }
    532         send_kwargs.update(settings)
--> 533         resp = self.send(prep, **send_kwargs)
    534 
    535         return resp

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\requests\sessions.py in send(self, request, **kwargs)
    644 
    645         # Send the request
--> 646         r = adapter.send(request, **kwargs)
    647 
    648         # Total elapsed time of the request (approximately)

C:\Users\mr-chen\Anaconda3\envs\hadoop\lib\site-packages\requests\adapters.py in send(self, request, stream, timeout, verify, cert, proxies)
    514                 raise SSLError(e, request=request)
    515 
--> 516             raise ConnectionError(e, request=request)
    517 
    518         except ClosedPoolError as e:

ConnectionError: HTTPConnectionPool(host='bigdata-senior03.chybinmy.com', port=50075): Max retries exceeded with url: /webhdfs/v1/data/ah.txt?op=CREATE&user.name=root&namenoderpcaddress=bigdata-senior01.chybinmy.com:8020&createflag=&createparent=true&overwrite=false (Caused by NewConnectionError(': Failed to establish a new connection: [Errno 11001] getaddrinfo failed',))

 

 

很明显，ConnectionError: HTTPConnectionPool(host='bigdata-senior03.chybinmy.com', port=50075)，这是我的数据节点的域名，没有在我python程序所在的主机上映射。

解决方案：

打开：C:\Windows\System32\drivers\etc

在hosts中加上ip和域名的映射：

问题成功解决。